Upload README.md with huggingface_hub

README.md

@@ -1,200 +1,65 @@
 ---
+license: mit
+library_name: setfit
 tags:
 - setfit
 - sentence-transformers
 - text-classification
-- generated_from_setfit_trainer
-widget:
-- text: Katibat Tulkarm (PIJ) and Al Aqsa Martyrs Brigade militants exchanged fire
-    with Israeli border police forces that raided Tulkarm (Tulkarm, West Bank). Militants
-    also targeted Israeli forces with explosives. In conjunction with the shooting,
-    Palestinian rioters clashed with the Israeli forces. Israeli forces fired live
-    and rubber-coated bullets, tear gas canisters, and stun grenades to disperse the
-    rioters. Israeli forces shot 3 Katibat Tulkarm militants during the clashes, injuring
-    them. All 3 later succumbed to their injuries, another 4 were also injured.
-- text: close to Barretos, Guanajuato, an armed individual shot and killed three other
-    men inside a parked vehicle on a dirt road. The armed individual then boarded
-    another vehicle driven by a second individual. 3 fatalities.
-- text: Russian forces fired 122mm artillery at Yastrubyne, Sumy. Casualties unknown.
-- text: Pro-Hadi forces manage to take a water project
-- text: Injuries are reported during protests to demand potable water, food, and energy
-    in Lara state, Venezuela
+- multi-label
+- water-conflict
 metrics:
+- f1
 - accuracy
-pipeline_tag: text-classification
-library_name: setfit
-inference: false
-base_model: BAAI/bge-small-en-v1.5
+language:
+- en
 ---
 
-# SetFit with BAAI/bge-small-en-v1.5
-
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) as the Sentence Transformer embedding model. A OneVsRestClassifier instance is used for classification.
-
-The model has been trained using an efficient few-shot learning technique that involves:
+# Water Conflict Multi-Label Classifier
 
-1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
-2. Training a classification head with features from the fine-tuned Sentence Transformer.
+This model classifies news headlines about water-related conflicts into three categories:
+- **Trigger**: Water resource as a conflict trigger
+- **Casualty**: Water infrastructure as a casualty/target
+- **Weapon**: Water used as a weapon/tool
 
 ## Model Details
 
-### Model Description
-- **Model Type:** SetFit
-- **Sentence Transformer body:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5)
-- **Classification head:** a OneVsRestClassifier instance
-- **Maximum Sequence Length:** 512 tokens
-- **Number of Classes:** 3 classes
-<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
-<!-- - **Language:** Unknown -->
-<!-- - **License:** Unknown -->
-
-### Model Sources
-
-- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
-- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
-- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
-
-## Uses
+- **Base Model**: BAAI/bge-small-en-v1.5
+- **Architecture**: SetFit with One-vs-Rest multi-label strategy
+- **Training Approach**: Few-shot learning optimized (SetFit reaches peak performance with small samples)
+- **Training Data**: 510 examples (sampled from ~5,000 labeled headlines)
+- **Performance**: F1 (micro) = 0.8319, Accuracy = 0.8333
 
-### Direct Use for Inference
-
-First install the SetFit library:
-
-```bash
-pip install setfit
-```
-
-Then you can load this model and run inference.
+## Usage
 
 ```python
 from setfit import SetFitModel
 
-# Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("baobabtech/water-conflict-classifier")
-# Run inference
-preds = model("Pro-Hadi forces manage to take a water project")
-```
-
-<!--
-### Downstream Use
-
-*List how someone could finetune this model on their own dataset.*
--->
 
-<!--
-### Out-of-Scope Use
+headlines = [
+    "Taliban attack workers at the Kajaki Dam in Afghanistan",
+    "New water treatment plant opens in California"
+]
 
-*List how the model may foreseeably be misused and address what users ought not to do with the model.*
--->
-
-<!--
-## Bias, Risks and Limitations
-
-*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
--->
-
-<!--
-### Recommendations
-
-*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
--->
-
-## Training Details
-
-### Training Set Metrics
-| Training set | Min | Median  | Max |
-|:-------------|:----|:--------|:----|
-| Word count   | 4   | 26.1843 | 167 |
-
-### Training Hyperparameters
-- batch_size: (32, 32)
-- num_epochs: (1, 1)
-- max_steps: -1
-- sampling_strategy: undersampling
-- body_learning_rate: (2e-05, 1e-05)
-- head_learning_rate: 0.01
-- loss: CosineSimilarityLoss
-- distance_metric: cosine_distance
-- margin: 0.25
-- end_to_end: False
-- use_amp: False
-- warmup_proportion: 0.1
-- l2_weight: 0.01
-- seed: 42
-- eval_max_steps: -1
-- load_best_model_at_end: True
-
-### Training Results
-| Epoch  | Step | Training Loss | Validation Loss |
-|:------:|:----:|:-------------:|:---------------:|
-| 0.0008 | 1    | 0.2363        | -               |
-| 0.0377 | 50   | 0.212         | -               |
-| 0.0754 | 100  | 0.1063        | -               |
-| 0.1131 | 150  | 0.0875        | -               |
-| 0.1508 | 200  | 0.0637        | -               |
-| 0.1885 | 250  | 0.0487        | -               |
-| 0.2262 | 300  | 0.0391        | -               |
-| 0.2640 | 350  | 0.0335        | -               |
-| 0.3017 | 400  | 0.0307        | -               |
-| 0.3394 | 450  | 0.027         | -               |
-| 0.3771 | 500  | 0.0274        | -               |
-| 0.4148 | 550  | 0.0273        | -               |
-| 0.4525 | 600  | 0.0298        | -               |
-| 0.4902 | 650  | 0.0267        | -               |
-| 0.5279 | 700  | 0.0242        | -               |
-| 0.5656 | 750  | 0.027         | -               |
-| 0.6033 | 800  | 0.0233        | -               |
-| 0.6410 | 850  | 0.027         | -               |
-| 0.6787 | 900  | 0.0225        | -               |
-| 0.7164 | 950  | 0.0237        | -               |
-| 0.7541 | 1000 | 0.0203        | -               |
-| 0.7919 | 1050 | 0.0193        | -               |
-| 0.8296 | 1100 | 0.0202        | -               |
-| 0.8673 | 1150 | 0.0202        | -               |
-| 0.9050 | 1200 | 0.0213        | -               |
-| 0.9427 | 1250 | 0.0216        | -               |
-| 0.9804 | 1300 | 0.019         | -               |
-| 1.0    | 1326 | -             | 0.0649          |
-
-### Framework Versions
-- Python: 3.12.12
-- SetFit: 1.1.3
-- Sentence Transformers: 5.1.2
-- Transformers: 4.57.3
-- PyTorch: 2.9.1+cu128
-- Datasets: 4.4.1
-- Tokenizers: 0.22.1
-
-## Citation
-
-### BibTeX
-```bibtex
-@article{https://doi.org/10.48550/arxiv.2209.11055,
-    doi = {10.48550/ARXIV.2209.11055},
-    url = {https://arxiv.org/abs/2209.11055},
-    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
-    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
-    title = {Efficient Few-Shot Learning Without Prompts},
-    publisher = {arXiv},
-    year = {2022},
-    copyright = {Creative Commons Attribution 4.0 International}
-}
+predictions = model.predict(headlines)
+print(predictions)
 ```
 
-<!--
-## Glossary
+## Training Metrics
 
-*Clearly define terms in order to be accessible across audiences.*
--->
+- Accuracy (exact match): 0.8333
+- F1 (micro): 0.8319
+- F1 (macro): 0.6755
+- Hamming Loss: 0.0704
 
-<!--
-## Model Card Authors
+## Label Distribution
 
-*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
--->
+| Label | F1 Score | Support |
+|-------|----------|---------|
+| Trigger | 0.8837 | 21 |
+| Casualty | 0.8571 | 30 |
+| Weapon | 0.2857 | 5 |
 
-<!--
-## Model Card Contact
+## Citation
 
-*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--->
+Based on ACLED (Armed Conflict Location & Event Data Project) data.